Related papers: DeepObfuscator: Obfuscating Intermediate Represent…

With increasing usage of deep learning algorithms in many application, new research questions related to privacy and adversarial attacks are emerging. However, the deep learning algorithm improvement needs more and more data to be shared…

Regarding image forensics, researchers have proposed various approaches to detect and/or localize manipulations, such as splices. Recent best performing image-forensics algorithms greatly benefit from the application of deep learning, but…

The widespread adoption of face recognition has led to increasing privacy concerns, as unauthorized access to face images can expose sensitive personal information. This paper explores face image protection against viewing and recovery…

Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment. Combined with the idea of adversarial training, preprocessing-based defenses are popular and…

Adversarial training and adversarial purification are two widely used defense strategies for enhancing model robustness against adversarial attacks. However, adversarial training requires costly retraining, while adversarial purification…

Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We design white-box inference attacks to perform a comprehensive privacy analysis of deep learning models. We measure…

Deep neural networks (DNNs) have proven to be quite effective in a vast array of machine learning tasks, with recent examples in cyber security and autonomous vehicles. Despite the superior performance of DNNs in these applications, it has…

The ubiquitous use of face recognition has sparked increasing privacy concerns, as unauthorized access to sensitive face images could compromise the information of individuals. This paper presents an in-depth study of the privacy protection…

Face images are rich data items that are useful and can easily be collected in many applications, such as in 1-to-1 face verification tasks in the domain of security and surveillance systems. Multiple methods have been proposed to protect…

Collaborative intelligence is a new paradigm for efficient deployment of deep neural networks across the mobile-cloud infrastructure. By dividing the network between the mobile and the cloud, it is possible to distribute the computational…

We investigate privacy-preserving, video-based action recognition in deep learning, a problem with growing importance in smart camera applications. A novel adversarial training framework is formulated to learn an anonymization transform for…

Massive human-related data is collected to train neural networks for computer vision tasks. A major conflict is exposed relating to software engineers between better developing AI systems and distancing from the sensitive training data. To…

We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model which is trained and evaluated based on information theoretic constraints. Using the selective exchange of information between a user's device and a service…

Recent deep learning models have shown remarkable performance in image classification. While these deep learning systems are getting closer to practical deployment, the common assumption made about data is that it does not carry any…

Federated learning is a promising distributed learning paradigm that enables collaborative model training without exposing local client data, thereby protecting data privacy. However, it also brings new threats and challenges. The…

Face recognition technology has been deployed in various real-life applications. The most sophisticated deep learning-based face recognition systems rely on training millions of face images through complex deep neural networks to achieve…

We propose adversarial embedding, a new steganography and watermarking technique that embeds secret information within images. The key idea of our method is to use deep neural networks for image classification and adversarial attacks to…

Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the input images. To address this vulnerability, adversarial training creates perturbation patterns and includes them in the training set to…

While widely adopted in practical applications, face recognition has been critically discussed regarding the malicious use of face images and the potential privacy problems, e.g., deceiving payment system and causing personal sabotage.…

Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the problem of obfuscated gradients. In this paper, we propose a…